Semantic Scholar Open Access 2021 55 sitasi

Recurrent Neural Network for Rain Estimation Using Commercial Microwave Links

H. Habi H. Messer

Abstrak

The use of recurrent neural networks ( $RNN\text{s}$ ) to utilize measurements from commercial microwave links ( $CML\text{s}$ ) has recently gained attention. Whereas previous studies focused on the performance of methods for wet–dry classification, here we propose an RNN algorithm for estimating the rain-rate. We empirically analyzed the proposed algorithm, using real data, and compared it with the traditional power-law (PL)-based algorithm, commonly used for estimating rain from CML attenuation measurements. Our analysis shows that the data-driven RNN algorithm, when properly trained, outperforms the PL algorithm in terms of accuracy. On the other hand, the PL algorithm is simpler and more robust when dealing with a large variety of corruptions and adverse conditions. We then introduced a time normalization (TN) layer for controlling the trade-off between performance and robustness of the RNN methods, and demonstrated its performance.

Topik & Kata Kunci

Penulis (2)

H

H. Habi

H

H. Messer

Format Sitasi

Habi, H., Messer, H. (2021). Recurrent Neural Network for Rain Estimation Using Commercial Microwave Links. https://doi.org/10.1109/TGRS.2020.3010305

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1109/TGRS.2020.3010305
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Total Sitasi
55×
Sumber Database
Semantic Scholar
DOI
10.1109/TGRS.2020.3010305
Akses
Open Access ✓